Merge remote-tracking branch 'upstream/master' into deepseek-v2

.github/ISSUE_TEMPLATE/01-bug-low.yml

@@ -0,0 +1,50 @@
+name: Low Severity Bugs
+description: Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
+title: "Bug: "
+labels: ["bug-unconfirmed", "low severity"]
+body:
+ - type: markdown
+ attributes:
+ value: |
+ Thanks for taking the time to fill out this bug report!
+ Please include information about your system, the steps to reproduce the bug,
+ and the version of llama.cpp that you are using.
+ If possible, please provide a minimal code example that reproduces the bug.
+ - type: textarea
+ id: what-happened
+ attributes:
+ label: What happened?
+ description: Also tell us, what did you expect to happen?
+ placeholder: Tell us what you see!
+ validations:
+ required: true
+ - type: textarea
+ id: version
+ attributes:
+ label: Name and Version
+ description: Which executable and which version of our software are you running? (use `--version` to get a version string)
+ placeholder: |
+ $./main --version
+ version: 2999 (42b4109e)
+ built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+ validations:
+ required: true
+ - type: dropdown
+ id: operating-system
+ attributes:
+ label: What operating system are you seeing the problem on?
+ multiple: true
+ options:
+ - Linux
+ - Mac
+ - Windows
+ - BSD
+ - Other? (Please let us know in description)
+ validations:
+ required: false
+ - type: textarea
+ id: logs
+ attributes:
+ label: Relevant log output
+ description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+ render: shell

.github/ISSUE_TEMPLATE/02-bug-medium.yml

@@ -0,0 +1,50 @@
+name: Medium Severity Bug
+description: Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but generally still useable)
+title: "Bug: "
+labels: ["bug-unconfirmed", "medium severity"]
+body:
+ - type: markdown
+ attributes:
+ value: |
+ Thanks for taking the time to fill out this bug report!
+ Please include information about your system, the steps to reproduce the bug,
+ and the version of llama.cpp that you are using.
+ If possible, please provide a minimal code example that reproduces the bug.
+ - type: textarea
+ id: what-happened
+ attributes:
+ label: What happened?
+ description: Also tell us, what did you expect to happen?
+ placeholder: Tell us what you see!
+ validations:
+ required: true
+ - type: textarea
+ id: version
+ attributes:
+ label: Name and Version
+ description: Which executable and which version of our software are you running? (use `--version` to get a version string)
+ placeholder: |
+ $./main --version
+ version: 2999 (42b4109e)
+ built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+ validations:
+ required: true
+ - type: dropdown
+ id: operating-system
+ attributes:
+ label: What operating system are you seeing the problem on?
+ multiple: true
+ options:
+ - Linux
+ - Mac
+ - Windows
+ - BSD
+ - Other? (Please let us know in description)
+ validations:
+ required: false
+ - type: textarea
+ id: logs
+ attributes:
+ label: Relevant log output
+ description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+ render: shell

.github/ISSUE_TEMPLATE/03-bug-high.yml

@@ -0,0 +1,50 @@
+name: High Severity Bug
+description: Used to report high severity bugs in llama.cpp (e.g. Malfunctioning features hindering important common workflow)
+title: "Bug: "
+labels: ["bug-unconfirmed", "high severity"]
+body:
+ - type: markdown
+ attributes:
+ value: |
+ Thanks for taking the time to fill out this bug report!
+ Please include information about your system, the steps to reproduce the bug,
+ and the version of llama.cpp that you are using.
+ If possible, please provide a minimal code example that reproduces the bug.
+ - type: textarea
+ id: what-happened
+ attributes:
+ label: What happened?
+ description: Also tell us, what did you expect to happen?
+ placeholder: Tell us what you see!
+ validations:
+ required: true
+ - type: textarea
+ id: version
+ attributes:
+ label: Name and Version
+ description: Which executable and which version of our software are you running? (use `--version` to get a version string)
+ placeholder: |
+ $./main --version
+ version: 2999 (42b4109e)
+ built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+ validations:
+ required: true
+ - type: dropdown
+ id: operating-system
+ attributes:
+ label: What operating system are you seeing the problem on?
+ multiple: true
+ options:
+ - Linux
+ - Mac
+ - Windows
+ - BSD
+ - Other? (Please let us know in description)
+ validations:
+ required: false
+ - type: textarea
+ id: logs
+ attributes:
+ label: Relevant log output
+ description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+ render: shell

.github/ISSUE_TEMPLATE/04-bug-critical.yml

@@ -0,0 +1,50 @@
+name: Critical Severity Bug
+description: Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
+title: "Bug: "
+labels: ["bug-unconfirmed", "critical severity"]
+body:
+ - type: markdown
+ attributes:
+ value: |
+ Thanks for taking the time to fill out this bug report!
+ Please include information about your system, the steps to reproduce the bug,
+ and the version of llama.cpp that you are using.
+ If possible, please provide a minimal code example that reproduces the bug.
+ - type: textarea
+ id: what-happened
+ attributes:
+ label: What happened?
+ description: Also tell us, what did you expect to happen?
+ placeholder: Tell us what you see!
+ validations:
+ required: true
+ - type: textarea
+ id: version
+ attributes:
+ label: Name and Version
+ description: Which executable and which version of our software are you running? (use `--version` to get a version string)
+ placeholder: |
+ $./main --version
+ version: 2999 (42b4109e)
+ built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+ validations:
+ required: true
+ - type: dropdown
+ id: operating-system
+ attributes:
+ label: What operating system are you seeing the problem on?
+ multiple: true
+ options:
+ - Linux
+ - Mac
+ - Windows
+ - BSD
+ - Other? (Please let us know in description)
+ validations:
+ required: false
+ - type: textarea
+ id: logs
+ attributes:
+ label: Relevant log output
+ description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+ render: shell

.github/ISSUE_TEMPLATE/05-enhancement.yml

@@ -0,0 +1,51 @@
+name: Enhancement template
+description: Used to request enhancements for llama.cpp
+title: "Feature Request: "
+labels: ["enhancement"]
+body:
+ - type: markdown
+ attributes:
+ value: |
+ [Please post your idea first in Discussion if there is not yet a consensus for this enhancement request. This will help to keep this issue tracker focused on enhancements that the community has agreed needs to be implemented.](https://github.com/ggerganov/llama.cpp/discussions/categories/ideas)
+
+ - type: checkboxes
+ id: prerequisites
+ attributes:
+ label: Prerequisites
+ description: Please confirm the following before submitting your enhancement request.
+ options:
+ - label: I am running the latest code. Mention the version if possible as well.
+ required: true
+ - label: I carefully followed the [README.md](https://github.com/ggerganov/llama.cpp/blob/master/README.md).
+ required: true
+ - label: I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
+ required: true
+ - label: I reviewed the [Discussions](https://github.com/ggerganov/llama.cpp/discussions), and have a new and useful enhancement to share.
+ required: true
+
+ - type: textarea
+ id: feature-description
+ attributes:
+ label: Feature Description
+ description: Please provide a detailed written description of what you were trying to do, and what you expected `llama.cpp` to do as an enhancement.
+ placeholder: Detailed description of the enhancement
+ validations:
+ required: true
+
+ - type: textarea
+ id: motivation
+ attributes:
+ label: Motivation
+ description: Please provide a detailed written description of reasons why this feature is necessary and how it is useful to `llama.cpp` users.
+ placeholder: Explanation of why this feature is needed and its benefits
+ validations:
+ required: true
+
+ - type: textarea
+ id: possible-implementation
+ attributes:
+ label: Possible Implementation
+ description: If you have an idea as to how it can be implemented, please write a detailed description. Feel free to give links to external sources or share visuals that might be helpful to understand the details better.
+ placeholder: Detailed description of potential implementation
+ validations:
+ required: false

.github/ISSUE_TEMPLATE/06-question.yml

@@ -0,0 +1,38 @@
+name: Question template
+description: Used to ask questions about llama.cpp
+title: "Question: "
+labels: ["question"]
+body:
+ - type: markdown
+ attributes:
+ value: |
+ [Please search your question first in Discussion if you got a common general question.](https://github.com/ggerganov/llama.cpp/discussions/categories/q-a)
+
+ - type: checkboxes
+ id: prerequisites
+ attributes:
+ label: Prerequisites
+ description: Please confirm the following before submitting your question.
+ options:
+ - label: I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
+ required: true
+ - label: I reviewed the [Discussions](https://github.com/ggerganov/llama.cpp/discussions), and have a new useful question to share that cannot be answered within Discussions.
+ required: true
+
+ - type: textarea
+ id: background-description
+ attributes:
+ label: Background Description
+ description: Please provide a detailed written description of what you were trying to do, and what you expected `llama.cpp` to do as an question.
+ placeholder: Detailed description of your question
+ validations:
+ required: true
+
+ - type: textarea
+ id: possible-answer
+ attributes:
+ label: Possible Answer
+ description: If you have some idea of possible answers you want to confirm, that would also be appreciated.
+ placeholder: Your idea of possible answers
+ validations:
+ required: false

.github/labeler.yml

@@ -1,5 +1,16 @@
 # https://github.com/actions/labeler
-
+Kompute:
+ - changed-files:
+ - any-glob-to-any-file:
+ - ggml-kompute.h
+ - ggml-kompute.cpp
+ - README-kompute.md
+Apple Metal:
+ - changed-files:
+ - any-glob-to-any-file:
+ - ggml-metal.h
+ - ggml-metal.cpp
+ - README-metal.md
 SYCL:
  - changed-files:
  - any-glob-to-any-file:
@@ -9,6 +20,7 @@ SYCL:
 Nvidia GPU:
  - changed-files:
  - any-glob-to-any-file:
+ - ggml-cuda.h
  - ggml-cuda/**
 Vulkan:
  - changed-files:

.github/workflows/docker.yml

@@ -42,8 +42,9 @@ jobs:
  - { tag: "light-rocm", dockerfile: ".devops/main-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
  - { tag: "full-rocm", dockerfile: ".devops/full-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
  - { tag: "server-rocm", dockerfile: ".devops/server-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- - { tag: "light-intel", dockerfile: ".devops/main-intel.Dockerfile", platforms: "linux/amd64" }
- - { tag: "server-intel", dockerfile: ".devops/server-intel.Dockerfile", platforms: "linux/amd64" }
+ # TODO: Disabled due to build issues https://github.com/ggerganov/llama.cpp/issues/7507
+ #- { tag: "light-intel", dockerfile: ".devops/main-intel.Dockerfile", platforms: "linux/amd64" }
+ #- { tag: "server-intel", dockerfile: ".devops/server-intel.Dockerfile", platforms: "linux/amd64" }
  steps:
  - name: Check out the repo
  uses: actions/checkout@v4

CMakeLists.txt

@@ -72,6 +72,7 @@ else()
  set(INS_ENB ON)
 endif()
 
+option(LLAMA_SVE "llama: enable SVE" OFF)
 option(LLAMA_AVX "llama: enable AVX" ${INS_ENB})
 option(LLAMA_AVX2 "llama: enable AVX2" ${INS_ENB})
 option(LLAMA_AVX512 "llama: enable AVX512" OFF)
@@ -1040,6 +1041,9 @@ if (CMAKE_OSX_ARCHITECTURES STREQUAL "arm64" OR CMAKE_GENERATOR_PLATFORM_LWR STR
  # Raspberry Pi 3, 4, Zero 2 (32-bit)
  list(APPEND ARCH_FLAGS -mno-unaligned-access)
  endif()
+ if (LLAMA_SVE)
+ list(APPEND ARCH_FLAGS -march=armv8.6-a+sve)
+ endif()
  endif()
 elseif (CMAKE_OSX_ARCHITECTURES STREQUAL "x86_64" OR CMAKE_GENERATOR_PLATFORM_LWR MATCHES "^(x86_64|i686|amd64|x64|win32)$" OR
  (NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_GENERATOR_PLATFORM_LWR AND